International Journal of Advances in Applied Sciences
Not a member yet
668 research outputs found
Sort by
Enrichment of microscopic photographs by utilizing CNN regarding soil-transmitted helminths identification
Get PDFSoil-transmitted helminth (STH) infection remains a significant global health challenge, affecting millions of people, particularly in developing countries. A convolutional neural network (CNN) approach to optimize the detection of STH infections in microscopic images. The study aims to assess the effectiveness of the CNN model in identifying and classifying STH worm eggs accurately. The research employs MATLAB as the primary tool for conducting experiments and validation tests. By implementing image preprocessing techniques to enhance image quality and applying precise segmentation methods, the CNN model is trained on a dataset of microscopic images to learn and classify STH infections effectively. The validation test results demonstrate that the CNN model achieved a high accuracy rate of 92.31% in classifying STH infections. This accuracy surpasses traditional methods, which are time-consuming and susceptible to human errors. This study underscores the importance of integrating artificial intelligence, particularly CNN, into the healthcare domain to support detecting and diagnosing diseases requiring specialized expertise, such as STH infections. The findings of this research can serve as a valuable reference for researchers, medical practitioners, and data scientists in leveraging artificial intelligence to enhance the quality of healthcare services, leading to positive impacts on society worldwide
Simulation and modeling for controlling stepper motor with tuned PID by GWO: comparative study
Get PDFThe current work aims to simulate the operation of the electric motor in one of the most important industrial applications, which is printers, by adopting stepper motors (SM). The performance of the motor is also improved by adopting traditional control systems and adjusting them using the gray wolf optimization (GWO) advanced algorithm. It works to adjust the parameters of a conventional controller. Simulation to reach an appropriate design with high performance, which is obtained by adopting the integral time absolute error (ITAE) function to get rid of the error for transient cases. Transfer function was adopted to represent the engine and two methods of control were used, traditional and advanced optimization. Results demonstrated the possibility of improving performance by adopting both methods with a clear superiority of advanced optimization. Response of SM without controller for close loop shows the values of each rising time equal 130.440 ms, overshoot equal 0.505%, and undershoot equal 1.077%. Response of SM for close loop with proportional-integral-derivative controllers (PIDC) shows the parameters, performance, and robustness of PIDC also the values of overshoot=9.16%, settling time=0.406, and rise time=0.0628 s. Results were developed by using GWO-PID over the previous cases by reducing values of overshoot to zero, rise time, and settling time to 0.00145 and 0.0027 respectively
Artificial intelligence-based cloud-internet of things resource management for energy conservation
Get PDFThe widespread demand for hosting application services in the cloud has been fueled by the deployment of cloud data centers (CDCs) on a global scale. Furthermore, modern apps' resource needs have sharply increased, especially in industries that use a lot of data. As a result, more cloud servers have been made available, resulting in higher energy usage and, ecological problems. Large-scale data centers have been developed as a result of the rapidly increasing demand for cloud services, allowing application service providers to rent data center space for application deployment by user-required quality of service (QoS). These data centers use a lot of electricity, which raises running expenses and produces more carbon dioxide (CO2) emissions. Modern cloud computing environments must also provide QoS for their users, necessitating a trade-off between power performance, energy consumption, and service-level agreement (SLA) compliance. We present an intelligent resource management policy using enforcement learning for CDCs. The objective is to continuously consolidate and dynamically allocate virtual machines (VMs). Utilizing live migration and disabling inactive nodes to reduce power consumption in this cloud environment while maintaining service quality. To enable dynamic resource management, a better power-performance tradeoff, and significantly lower energy consumption, we integrate several artificial intelligence concepts. Based on the result the proposed approach is more efficient as compared with other techniques
A novel reduced-switch multi-level inverter based multi-device universal power-quality conditioner for PQ enhancement
Get PDFThe reduced-switch multilevel inverter (RSMLI) has garnered significant attention across various industries as a viable alternative to conventional multilevel inverter (MLI) topologies. In the realm of medium voltage high-power applications, the topologies of resonant switched MLIs are regarded as advanced due to their development with a reduced number of switching elements. The primary emphasis of the customizable multi-device universal power-quality conditioner (MD-UPQC) device is on the design and development of a significant RSMLI topology to improve power-quality (PQ) features. This study presents the development of a novel 5-level RSMLI-based MD-UPQC device, designed specifically for addressing power-quality concerns in multi-feeder distribution networks. The device facilitates uninterrupted power flow between the feeders, thereby mitigating power-quality issues. The 5-level RSMLI topology possesses the capability to decrease the necessity for a larger quantity of gate-drive circuits by implementing a switching-logic design utilizing the reduced-carrier-based pulse width modulation (PWM) technique. The 5-level RSMLI-MDUPQC device incorporates a unified voltage-current reference (UVCR) control scheme to ensure efficient operation. The functionality and efficacy of the proposed RSMLI-MDUPQC device have been assessed using the MATLAB/Simulink software tool, with the evaluation conducted under different PQ conditions. The simulation outcomes are presented for analysis and interpretation
Automatic slice thickness measurement on computed tomography images of American College of Radiology phantom
Get PDFThis study aims to develop an automatic method for calculating slice thickness on an American College of Radiology (ACR) phantom and evaluate its accuracy at variations of orientation angle and slice thickness. The phantom was scanned using Siemens SOMATOM perspective, with variations of the slice thickness (i.e. 1.5, 3, 5, 6, 7, and 10 mm) and rotation angles (i.e. 0.0, 22.5, 45.0, and 67.5°). The phantom rotation was based on the bone object as a reference. After determining the rotation angle, the phantom image was rotated by the angle. Next, profiles of pixel values across the wire objects for measuring slice thickness were developed from rotated phantom images. The slice thickness was measured automatically from the obtained profiles. The results of the automated method are 2.5, 4.1, 5.4, 5.8, 7.8, and 9.8 mm for all varied slice thicknesses. The differences between the automatic and manual methods are within 0.3 mm. The automatic method is capable of detecting slice thickness for various angles. The differences in slice thickness for various angles are within 0.1 mm for a slice thickness of 3 mm. These results are similar when compared to manual measurements. An algorithm for automated slice thickness measurement on ACR phantom has been successfully developed
Determinants of community participation in ecotourism programs in Bali, Indonesia
Get PDFIn the case of Indonesia, most of the tourist attractions offered and advertised are protected forests. This research seeks to find a balance between these two interests, so the purpose of this research is actually to determine the determinants of local community involvement in ecotourism development in Bali. This research uses quantitative methods described in the form of descriptive, and factor analysis according to the results of the survey with informants in the ecotourism of West Bali National Park, Buyan Tamblingan, Bali Mangrove, Batur Kintamani, and Lembongan. Eight factors determine community participation in ecotourism programs in Bali, namely: i) the role of leaders and business opportunities, ii) the factor of mindset and industry cooperation, iii) the factor of income, socialization, and commitment, iv) the factor of awareness of nature conservation, v) the factor of optimism to get money and knowledge, vi) the factor of facilities and independence, vii) the factor of training, interest, and participation, and viii) the factor of skills and funding
Study of Babak River water quality using physical and chemical parameters in Kebon Kongok landfill (Lombok, Indonesia)
Get PDFThe study has been conducted on the water quality level of the Babak River around Kebon Kongok landfill, Lombok. This research was conducted considering that water has many benefits in the daily lives of people. This research uses an experimental method by analyzing physical parameters (temperature, conductivity, pH, and total dissolved solids (TDS)), and chemical parameters in the form of heavy metal content lead (Pb), iron (Fe), manganese (Mn), and copper (Cu)). Analysis results were compared with quality standards based on Ministry of Health Regulation No. 32 of 2017 concerning water quality. Based on the study, it was found that the farther the distance of water measured from the source of pollution, the value of the physical and chemical parameters of water will be smaller. Most of the physical parameter test results show the Babak River water quality is still at the safe threshold limit but there is 1 point of river water that is polluted due to the distance that is too close to the active zone. Chemical parameters show the results of heavy metal content below the threshold limit. Analysis of the water quality shows that the water is still in good condition, which is below the threshold set by the Indonesian government
TherapyBot: a chatbot for mental well-being using transformers
Get PDFThe field of natural language processing (NLP) and conversational artificial intelligence (AI) has one ingenious application in the psychological space. Depression and anxiety are two major issues that the world is facing, with close to 41% of adults reporting these symptoms in the United States alone, as of December 2020. It has also been observed that most of the people are not open about it. As a result, it is critical to address this issue on a global scale. Developed countries reportedly have 9 psychiatrists per 100,000 people. One way to mitigate this is the use of chatbots. We propose a transformer-based methodology to build a therapy bot that has been trained on a combination of open-domain conversations from a publicly available dataset and therapist-client conversations from a self-constructed dataset. This end-to-end data-driven model shows quality performance in conversations and adds value by aiding in the case of mental health issues. The proposed architecture is proven to be effective in its usability in the psychological space for both single-turn and multi-turn dialogue. The performance of the proposed system shows loss is 0.29 and perplexity is 1.34, both metrics keeps gradually decreasing and it means an improvement in performance of chatbots system
Usability analysis of marker-based augmented reality application for the microcontroller study
Get PDFVirtual labs using augmented reality (AR) applications have brought transformation in teaching laboratory courses. However, in the field of engineering laboratories, the use of AR applications is still new. In this work, a marker-based AR application is used as a tool that enables a hands-on learning experience of microcontroller study. The software used to develop this application are Unity3D and Vuforia. C# programming language has also been used to provide the command for the interaction between the interface and the application. After the development of the application was complete, it was tested by a group of electrical engineering students. Then, the students are required to fill out a survey on the system usability scale (SUS) test. The SUS score of this application is 62.5. It was found that the perceived usability of the evaluated AR application as a teaching tool for laboratory courses is acceptable. This response shows the marker-based AR application has the potential to be used as a teaching aid in engineering laboratory courses
Ecological assessment of pastures semi-deserts and dry steppes of Azerbaijan
Get PDFThe absence in the scientific literature of criteria for assessing the ecological status of pasture lands, insufficient knowledge of the use of predictive methods and technology for carrying out special agrochemical measures, as well as issues of permissible loads, served as the basis for choosing the topic of research work. For the first time, in the conditions of pastures in Azerbaijan, an environmental and energy assessment of soil-landscape complexes was carried out. A detailed and final quality assessment was drawn up on soil scale, and the coefficient of their comparative merit was determined. A scientifically based system of agrochemical measures for the superficial and fundamental improvement of pastures has been developed. The final bonitet scale, reflecting the level of fertility of soil varieties, showed that the soils of the Jeyranchol massif turned out to be the most fertile at 62 points, compared with them, the pasture soils of Ajinohur on average across the massif received 53 points, Gobustan 51 points, and the Kura-Araz lowland 55 points. On average, pasture lands in Azerbaijan are valued at 55 points, which indicates the need for agro-reclamation measures. The types of forage plants are distributed as follows: i) Cereals 116, 12%; ii) Asteraceae 109, 11.2%; iii) Legumes 82, 8.4%; iv) Brassicas 59, 6.2%; 6%; v) Cloves 50, 5.3%; vi) Lamiaceae 42, 4.6%; vii) Linear 40, 4.2%; viii) Goosefoot 6, ix) Gimletaceae 32 species, 3.4%; x) Umbrellas 38, 4.4%; xi) Other 339 types, 35.5%